LAB #2713 NEUTRAL: LEDGER BENCH: Apply filter: XAUUSD LONG @ ASIAN with 5 conf — improves win rate from 30.9% to 66.7% — E8 Intelligence Research

IDEA: Adjustment made to the live model — verify against the backtests: Apply filter: XAUUSD LONG @ ASIAN with 5 conf — improves win rate from 30.9% to 66.7% (+35.7pp, n=21) SAME-WINDOW EFFECT: Over the current live window, the filter would have blocked the XAUUSD LONG @ 4270.17 (rizzy7m, 2026-08-06) — which was a WIN — and the XAUUSD SHORT @ 4048.74 (rizzy5m, 2026-08-04) — a LOSS. Net effect: removes one win and one loss, so win-rate delta is roughly neutral (2 of 3 remaining XAU trades are losses, but those are SHORTs, not LONGs). The filter targets LONGs only, so the only LONG in the window is a win — applying it would have reduced total wins by 1, lowering overall win rate from 6/10 to 5/9 (55.6% vs 60%), and PnL would drop by the size of that winning trade. This is a small, negative immediate impact — the filter would have hurt live performance in this specific window. OVER-TIME PROJECTION: The backtest claims +35.7pp on n=21, but that is a tiny sample with high variance — a sin Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com